A Systematic Review: Deep Learning based E-Learning Recommendation System

Bhanuse, Roshan; Mal, Sandip

doi:10.1109/icais50930.2021.9395835

Cited by 16 publications

(7 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The predictive capabilities of ANNs extend to detecting undesirable student behavior, with contributions from Fei and Yeung [48], Teruel and Alemany [49], and Whitehill et al [50]. Furthermore, ANNs have been instrumental in generating recommendations, as evidenced by the studies of Abhinav et al [51], Algarni and Sheldon [11], Bhanuse and Mal [7], and Wong [52]. For instance, Abhinav et al [51] introduced a recommendation system that leverages ANNs for content-based filtering, alongside collaborative filtering techniques, to personalize learning opportunities.…”

Section: Neural Network In Educationmentioning

confidence: 99%

“…The key distinction lies in the explicit representation of knowledge in symbolic AI versus the more implicit, data-driven approach of sub-symbolic methods. As a result, sub-symbolic methods like deep neural networks, which belong to the family of artificial neural networks (ANNs), have gained considerable popularity in various educational tasks, including learner modeling (e.g., [7][8][9][10][11]). Despite their success and popularity, they face three primary challenges that limit their educational value.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Augmenting Deep Neural Networks with Symbolic Educational Knowledge: Towards Trustworthy and Interpretable AI for Education

Hooshyar,

Azevedo,

Yang

2024

MAKE

View full text Add to dashboard Cite

Artificial neural networks (ANNs) have proven to be among the most important artificial intelligence (AI) techniques in educational applications, providing adaptive educational services. However, their educational potential is limited in practice due to challenges such as the following: (i) the difficulties in incorporating symbolic educational knowledge (e.g., causal relationships and practitioners’ knowledge) in their development, (ii) a propensity to learn and reflect biases, and (iii) a lack of interpretability. As education is classified as a ‘high-risk’ domain under recent regulatory frameworks like the EU AI Act—highlighting its influence on individual futures and discrimination risks—integrating educational insights into ANNs is essential. This ensures that AI applications adhere to essential educational restrictions and provide interpretable predictions. This research introduces NSAI, a neural-symbolic AI approach that integrates neural networks with knowledge representation and symbolic reasoning. It injects and extracts educational knowledge into and from deep neural networks to model learners’ computational thinking, aiming to enhance personalized learning and develop computational thinking skills. Our findings revealed that the NSAI approach demonstrates better generalizability compared to deep neural networks trained on both original training data and data enriched by SMOTE and autoencoder methods. More importantly, we found that, unlike traditional deep neural networks, which mainly relied on spurious correlations in their predictions, the NSAI approach prioritizes the development of robust representations that accurately capture causal relationships between inputs and outputs. This focus significantly reduces the reinforcement of biases and prevents misleading correlations in the models. Furthermore, our research showed that the NSAI approach enables the extraction of rules from the trained network, facilitating interpretation and reasoning during the path to predictions, as well as refining the initial educational knowledge. These findings imply that neural-symbolic AI not only overcomes the limitations of ANNs in education but also holds broader potential for transforming educational practices and outcomes through trustworthy and interpretable applications.

show abstract

Section: Neural Network In Educationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Augmenting Deep Neural Networks with Symbolic Educational Knowledge: Towards Trustworthy and Interpretable AI for Education

Hooshyar,

Azevedo,

Yang

2024

MAKE

View full text Add to dashboard Cite

show abstract

“…For designers, the significant influences of PE, EE and SI found in the study warrant optimizing perceived usefulness, effort minimization and social connectivity through system features. Functions like personalized goal-setting (Katsaris and Vidakis, 2021), dynamic recommendations (Bhanuse and Mal, 2021) and easy layout navigation (Sabri et al, 2022) delivered through a mobile platform can bolster usefulness while reducing effort. Stringent data and privacy security are also important to help alleviate anxiety for neurotic mature students.…”

Section: Practical Implicationsmentioning

confidence: 99%

Understanding mature students' intention to use mobile learning in higher education: integrating personality traits and UTAUT

Chau

2024

IJEM

View full text Add to dashboard Cite

PurposeThis study aims to provide new insights into the relationship between individual characteristics, particularly personality traits and mature students' intention to use (ITU) mobile learning (m-learning).Design/methodology/approachThe research model was constructed by integrating the Big Five personality traits into the unified theory of acceptance and use of technology (UTAUT) model. The data were collected from mature students at a university research center in Macau. Partial least squares structural equation modeling (PLS-SEM) was used to analyze the data and test the proposed hypotheses.FindingsThe results reveal that personality traits play a significant role in determining mature students' ITU m-learning technology. In particular, social influence (SI) mediates the relationship between agreeableness (AGB) and ITU.Originality/valueThis study examines how personality traits collectively influence mature students' receptiveness and intentions toward m-learning. As mature learners' motivations and preferences remain underexplored, insights into trait-technology links could address current gaps and optimize mobile educational support tailored to their distinct characteristics and needs.

show abstract

“…The results of performance evaluation proved that this system was suitable for recommending content to the online learners. Many researchers reviewed the limitation of the recommender systems (10) system so that the better recommender system can be proposed (11).…”

Section: Related Workmentioning

confidence: 99%

Towards Analyzing the Online Learner's Behavior: An Expedition to Recommender System

Kaur¹,

Gupta²,

Madhukar³

2022

ECS Trans.

View full text Add to dashboard Cite

E-learning courses are gaining significance nowadays and are also an active area for research. COVID-19 pandemic has challenged education system across the globe and many institutions have switched to the online platforms for survival. Due to this, a lot many online courses are available and it is very difficult for a novice user to select suitable course as per one’s preference. Despite the great motivation for MOOC courses and rapid growth of online platforms, there has been tremendous drop out for MOOC courses. This paper focuses on analyzing user activities or user’s learning behavior in order to recommend suitable and unsuitable courses according to user preference. One of the key issues is nowadays is the increasing dropout rate of MOOC learners. The completion rate of most of the online courses is very less as compared to the number of enrolled participants. After creating and analyzing the user learners’ profile, the recommender system recommends suitable courses to the learners so that dropout cases will decrease and the user will be able to choose appropriate courses as per their preferences. Sometimes under social influence or lack of awareness, learners opt those courses that are not appropriate for them. As each learner knowledge level is diverse so customization is required in order to improve online learning experience. In this paper, authors have described various challenges of the online learners, suggested how a recommender system should be advanced and different types of recommender systems.

show abstract

A Systematic Review: Deep Learning based E-Learning Recommendation System

Cited by 16 publications

References 49 publications

Augmenting Deep Neural Networks with Symbolic Educational Knowledge: Towards Trustworthy and Interpretable AI for Education

Augmenting Deep Neural Networks with Symbolic Educational Knowledge: Towards Trustworthy and Interpretable AI for Education

Understanding mature students' intention to use mobile learning in higher education: integrating personality traits and UTAUT

Towards Analyzing the Online Learner's Behavior: An Expedition to Recommender System

Contact Info

Product

Resources

About